CN109284871A - Resource adjusting method, device and cloud platform - Google Patents
Resource adjusting method, device and cloud platform Download PDFInfo
- Publication number
- CN109284871A CN109284871A CN201811166697.4A CN201811166697A CN109284871A CN 109284871 A CN109284871 A CN 109284871A CN 201811166697 A CN201811166697 A CN 201811166697A CN 109284871 A CN109284871 A CN 109284871A
- Authority
- CN
- China
- Prior art keywords
- service
- resource
- resource node
- node
- prediction
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06315—Needs-based resource requirements planning or analysis
Abstract
The present invention provides a kind of resource adjusting method, device and cloud platforms, wherein this method is applied to the monitoring node of cloud platform, which is connected with multiple resource nodes, and operation has service on resource node;This method comprises: obtaining in preset time period, the history data of resource node;History data is input in preset resources model, to export the prediction result for servicing current desired resource;Preset resources model is established by way of machine learning;The resource node of operation service is adjusted according to prediction result.The present invention establishes resources model by way of machine learning, according to the resource of the prediction result adjustment service of resources model output, to make the actual demand of resource and service match, while guarantee system operates normally, cloud platform resource utilization is improved, the use cost of platform user has been saved.
Description
Technical field
The present invention relates to field of cloud computer technology, more particularly, to a kind of resource adjusting method, device and cloud platform.
Background technique
In order to save hardware cost, computing resource operation service or execute calculating times that user can rent in cloud platform
Business;In existing mode, cloud platform provides the resource of fixed size generally according to the rental demand of user for user;Work as business
When amount increases, the resource being currently rented by may not be able to meet business demand, service impacting normal operation;And work as the industry of the user
When business amount reduces, the resource rented can be idle, so that platform resource utilization rate is lower, wastes making for user to a certain extent
Use cost.
Summary of the invention
In view of this, the purpose of the present invention is to provide a kind of resource adjusting method, device and cloud platform so that resource with
The actual demand of service matches, and while guaranteeing that system operates normally, improves cloud platform resource utilization, saves platform user
Use cost.
In a first aspect, the embodiment of the invention provides a kind of resource adjusting methods, wherein this method is applied to cloud platform
Node is monitored, monitoring node is connected with multiple resource nodes, and operation has service on resource node;This method comprises: obtaining default
In period, the history data of resource node;History data includes the cpu busy percentage of resource node, memory utilization
Rate, network interface card go out inbound traffics, monitor goes out inbound traffics and at least one of data Packet Forwarding Rate;History data is input to
In preset resources model, to export the prediction result for servicing current desired resource;Preset resources model passes through
The mode of machine learning is established;According to prediction result, the resource node of operation service is adjusted.
With reference to first aspect, the embodiment of the invention provides the first possible embodiments of first aspect, wherein pre-
If resources model established especially by following manner: obtain training sample data;Comprising at least in training sample data
The operation sample data of one service, and the corresponding resource of operation sample data adjust data;Build initial model structure;
Training sample data are input to initial model structure to be trained, obtain resources model.
With reference to first aspect, the embodiment of the invention provides second of possible embodiments of first aspect, wherein pre-
Survey the prediction total resources in result including operation service;It is above-mentioned according to prediction result, adjust the resource node packet of operation service
It includes: the real resource total amount of comparison prediction total resources and the resource node of current operation service;According to comparison result, increase or
Reduce the resource node of current operation service.
The possible embodiment of second with reference to first aspect, the embodiment of the invention provides the third of first aspect
Possible embodiment, wherein the real resource of above-mentioned comparison prediction total resources and the resource node of current operation service is total
Amount includes: to determine the prediction number of nodes of operation service according to the unit resource amount of prediction total resources and resource node;Compare
Predict the resource node quantity of number of nodes and current operation service;It is above-mentioned according to comparison result, increase or decrease current operation
If the resource node of service includes: to predict that number of nodes is greater than the resource node quantity of current operation service, saved according to prediction
Point quantity increases the resource node of operation service;If predicting that number of nodes is less than the resource node quantity of current operation service,
The resource node of operation service is reduced according to prediction number of nodes.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 4th kind of first aspect
Possible embodiment, wherein comprise determining that money to be increased according to the resource node that prediction number of nodes increases operation service
Source node;Obtain the image file of service;The operating parameter of increased resource node is set;Operating parameter includes at least resource section
The data transfer bandwidth of point;Image file is deployed in increased resource node, which is arranged in the resource section
Point in;According to operating parameter operation service.
The third possible embodiment with reference to first aspect, the embodiment of the invention provides the 5th kind of first aspect
Possible embodiment, wherein before the step of reducing the resource node of operation service according to prediction number of nodes, this method packet
It includes: determining resource node to be deleted;It recycles in resource node to be deleted, the operation data of service;Operation data is shifted
Into the resource node in addition to resource node to be deleted;Service in the resource node to be deleted is deleted.
The possible embodiment of with reference to first aspect the first, the embodiment of the invention provides the 6th kind of first aspect
Possible embodiment, wherein after output services the step of prediction result of current desired resource, this method further include: root
It is predicted that result updates training sample data;Resources model is input to using the training sample data of update to be trained,
With the resources model updated.
Second aspect, the embodiment of the invention also provides a kind of resources to adjust device, wherein the device is applied to cloud platform
Monitoring node, monitoring node is connected with multiple resource nodes, and operation has service on resource node;The device includes: that data obtain
Modulus block, for obtaining in preset time period, the history data of resource node;History data includes resource node
Cpu busy percentage, memory usage, network interface card go out inbound traffics, monitor goes out inbound traffics and at least one of data Packet Forwarding Rate;In advance
Module is surveyed, for history data to be input in preset resources model, services current desired resource to export
Prediction result;Preset resources model is established by way of machine learning;Module is adjusted, is used for according to prediction result,
Adjust the resource node of operation service.
In conjunction with second aspect, the embodiment of the invention provides the first possible embodiments of second aspect, wherein on
Stating device further includes machine learning module, which is used for: obtaining training sample data;It is wrapped in training sample data
Operation sample data containing at least one service, and the corresponding resource of operation sample data adjust data;Build initial mould
Type structure;Training sample data are input to initial model structure to be trained, obtain resources model.
In conjunction with second aspect, the embodiment of the invention provides second of possible embodiments of second aspect, wherein pre-
Survey the prediction total resources that result includes operation service;The adjustment module is used for: comparison prediction total resources and current operation
The real resource total amount of the resource node of service;According to comparison result, the resource node of current operation service is increased or decreased.
In conjunction with second of possible embodiment of second aspect, the embodiment of the invention provides the third of second aspect
Possible embodiment, wherein it is described adjustment module be used for: according to prediction total resources and resource node unit resource amount,
Determine the prediction number of nodes of operation service;If predicting that number of nodes is greater than the resource node quantity of current operation service, press
Increase the resource node of operation service according to prediction number of nodes;If predicting that number of nodes is less than the resource section of current operation service
Point quantity reduces the resource node of operation service according to prediction number of nodes.
In conjunction with the third possible embodiment of second aspect, the embodiment of the invention provides the 4th kind of second aspect
Possible embodiment, wherein the adjustment module is used for: determining resource node to be increased;Obtain the image file of service;If
Set the operating parameter of increased resource node;Operating parameter includes at least the data transfer bandwidth of resource node;By image file
It is deployed in increased resource node, which is arranged in the resource node;According to operating parameter operation service.
In conjunction with the third possible embodiment of second aspect, the embodiment of the invention provides the 5th kind of second aspect
Possible embodiment, wherein the adjustment module is used for: determining resource node to be deleted;Recycle resource node to be deleted
In, the operation data of service;Operation data is transferred in the resource node in addition to resource node to be deleted;It will be to be deleted
Resource node in service delete.
In conjunction with the first possible embodiment of second aspect, the embodiment of the invention provides the 6th kind of second aspect
Possible embodiment, wherein the device further include: data update module, for updating number of training according to prediction result
According to;Training module is input to resources model for the training sample data using update and is trained, with what is updated
The resources model.
The third aspect, the embodiment of the invention also provides a kind of cloud platforms, wherein the cloud platform includes monitoring node and money
Source node;Monitoring node is connected with multiple resource nodes, and operation has service on resource node;Resource node includes operation node
And/or memory node;Device described in second aspect is set to monitoring node.
Fourth aspect, the embodiment of the invention also provides a kind of server, including processor and memory, memory storages
There is the machine-executable instruction that can be executed by processor, processor executes machine-executable instruction to realize above-mentioned resource adjustment
Method.
5th aspect, the embodiment of the invention also provides a kind of machine readable storage mediums, which is characterized in that the machine can
It reads storage medium and is stored with machine-executable instruction, for the machine-executable instruction when being called and being executed by processor, machine can
It executes instruction and processor is promoted to realize above-mentioned resource adjusting method.
The embodiment of the present invention bring it is following the utility model has the advantages that
The embodiment of the invention provides a kind of resource adjusting method, device, cloud platform server and machine readable storage Jie
Matter establishes resources model by way of machine learning, and the history data for servicing corresponding resource node is inputted
To in preset resources model, can predict to obtain the prediction result for servicing current desired resource;And then further according to prediction
As a result the resource node of operation service is adjusted.Which establishes resources model by way of machine learning, according to resource
The resource of the prediction result adjustment service of prediction model output guarantees system so that the actual demand of resource and service be made to match
While system operates normally, cloud platform resource utilization is improved, the use cost of platform user has been saved.
Other features and advantages of the present invention will illustrate in the following description, alternatively, Partial Feature and advantage can be with
Deduce from specification or unambiguously determine, or by implementing above-mentioned technology of the invention it can be learnt that.
To enable the above objects, features and advantages of the present invention to be clearer and more comprehensible, better embodiment is cited below particularly, and match
Appended attached drawing is closed, is described in detail below.
Detailed description of the invention
It, below will be to specific in order to illustrate more clearly of the specific embodiment of the invention or technical solution in the prior art
Embodiment or attached drawing needed to be used in the description of the prior art be briefly described, it should be apparent that, it is described below
Attached drawing is some embodiments of the present invention, for those of ordinary skill in the art, before not making the creative labor
It puts, is also possible to obtain other drawings based on these drawings.
Fig. 1 is a kind of structural schematic diagram of cloud platform provided in an embodiment of the present invention;
Fig. 2 is a kind of flow chart of resource adjusting method provided in an embodiment of the present invention;
Fig. 3 is a kind of flow chart for the method for establishing resources model provided in an embodiment of the present invention;
Fig. 4 is the flow chart of another resource adjusting method provided in an embodiment of the present invention;
Fig. 5 is to increase the flow chart of resource node in another resource adjusting method provided in an embodiment of the present invention;
Fig. 6 is to reduce the flow chart of resource node in another resource adjusting method provided in an embodiment of the present invention;
Fig. 7 is the structural schematic diagram that a kind of resource provided in an embodiment of the present invention adjusts device;
Fig. 8 is a kind of structural schematic diagram of Cloud Server provided in an embodiment of the present invention.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with attached drawing to the present invention
Technical solution be clearly and completely described, it is clear that described embodiments are some of the embodiments of the present invention, rather than
Whole embodiments.Based on the embodiments of the present invention, those of ordinary skill in the art are not making creative work premise
Under every other embodiment obtained, shall fall within the protection scope of the present invention.
In order to make it easy to understand, a kind of cloud platform is described first below, as the application scenarios of the embodiment of the present invention, referring to figure
A kind of structural schematic diagram of cloud platform shown in 1, is provided with monitoring node in cloud platform, and each monitoring monitoring nodes set model
It encloses or the resource node of quantity;It is illustrated by taking a monitoring node as an example in Fig. 1, which is connected with multiple resource sections
Point, the resource node include operation node and memory node, with three operation nodes of monitoring monitoring nodes and three in Fig. 1
For memory node;Operation has service on resource node, such as information management system, instant communicating system, shopping website system
Deng.
The resource of fixed size is usually rented in each service, for example, the operation node and memory node of specified quantity.Cloud
Platform is generally supplied to the resource of user's fixed size according to the rental demand of user in advance, but due to servicing in operational process
In, number of users, amount of access, data volume etc. are all being constantly occurring variation, service the actual demand to resource also continuous
It changes;When portfolio increases, the resource of current operation service may be insufficient for business demand, easily lead to service
Performance substantially reduces or even service impacting normal operation;When portfolio is reduced, the resource of service can leave unused again, so that cloud
The resource of platform cannot get reasonable utilization, reduce utilization rate resource, to a certain extent to user rent cloud platform at
Originally it causes to waste.
In order to avoid the above problem, the resource of operation service is needed to change at any time with the business demand of service, is based on this,
The embodiment of the invention provides a kind of resource adjusting method, device and cloud platform, which can be applied to provide various cloud clothes
In the cloud platform of business.It is specifically introduced below by embodiment.
A kind of flow chart of resource adjusting method shown in Figure 2, this method are applied to the monitoring node of cloud platform, should
Monitoring node is connected with multiple resource nodes, and operation has service on resource node;The resource node can be operation node or deposit
Store up node;In most cases, service had both needed operation node in the process of running, it is also desirable to memory node;Therefore, above-mentioned
Resource node usually includes operation node and memory node simultaneously;But in some special cases, for example, being exclusively used in storing data
Service, may only need memory node;At this point, resource node can be only comprising operation one of node or memory node.
The method steps are as follows:
Step S202 is obtained in preset time period, the history data of resource node;The history data includes money
CPU (Central Processing Unit/Processor, central processing unit) utilization rate, memory usage, net of source node
Block inbound traffics, monitor out go out it is a variety of in inbound traffics and data Packet Forwarding Rate.
In the initial operating stage of service, cloud platform can be the resource of service distribution fixed size according to the demand of user;Clothes
Corresponding resource node of being engaged in runs the resource node of the service.In system operation, acquisition runs each money of the service
The history data of source node;Specifically, above-mentioned preset time period is usually the period of regular length;In practical realization
When, history data can be obtained by the way of periodically getting ready;Specifically, it every certain period of time, obtains above-mentioned pre-
If the history data in the period;For example, obtaining the history run of each resource node in this ten minutes every ten minutes
Data;The history data of each resource node in nearest one minute can also be obtained every ten minutes.
In above-mentioned history data, CPU percentage that when cpu busy percentage, that is, resource node operation service program occupies
Than;If cpu busy percentage is lower, illustrate that the resource node utilization rate is lower;If cpu busy percentage is higher, illustrate the resource section
Point utilization rate is higher, but when cpu busy percentage is excessively high, will affect the speed of service of the program of service, leads to performance, the response of service
Speed decline;In addition, CPU usage is excessively high, to will lead to cpu temperature in resource node excessively high, can greatly shorten the CPU service life.It is above-mentioned
The memory percentage occupied when memory usage, that is, resource node operation service program, it is similar with above-mentioned cpu busy percentage, if
Memory usage is lower, illustrates that the resource node utilization rate is lower;If memory usage is higher, illustrate that the resource node utilizes
Rate is higher, but when memory usage is excessively high, also will affect the speed of service of the program of service, and then influence service performance.
Above-mentioned network interface card goes out the inbound traffics i.e. upstream data of the resource node and downlink data amount, if network interface card go out inbound traffics compared with
Height usually illustrates that the service access amount is larger.Monitor can be set on monitoring node or resource node, which can be with
It is realized by software program;The monitor room can be used for monitoring specified resource node, designated virtual machine or specified data type
Flow;Above-mentioned monitor, which goes out inbound traffics, may indicate that the amount of access of certain particular module functions in service.Above-mentioned data packet forwarding
Rate commonly used to measure resource node data throughput capabilities and data-handling capacity, when resource node data Packet Forwarding Rate compared with
Gao Shi, it may also be said to which the portfolio of bright service is larger.
Above-mentioned history data is input in preset resources model by step S204, current with output service
The prediction result of required resource.
Above-mentioned preset resources model can be established by way of machine learning.The model is detailed below
Establish mode;It is shown in Figure 3, the specific steps are as follows:
Step S302 obtains training sample data;Operation sample comprising at least one service in the training sample data
Data, and the corresponding resource of operation sample data adjust data;
The training sample data used are crossed in generating model process, can derive from current service, i.e., above-mentioned progress
The service of resource adjustment, can also be from other services;The operation sample data equally may include the CPU of resource node
Utilization rate, memory usage, network interface card go out inbound traffics, monitor goes out inbound traffics and data Packet Forwarding Rate etc.;For example, can be by fixed
When the mode that acquires obtain multiple groups operation sample data;The corresponding resource adjustment data of every group of operation sample data can be by engineering
Teacher's manual setting based on practical experience.
Step S304 builds initial model structure;
Initial model structure can specifically be selected according to actual needs, for example, neural network model, supporting vector
Machine model, trend extropolation prediction model, regressive prediction model, combination forecasting etc..
Training sample data are input to initial model structure and are trained, obtain resources model by step S306.
By taking regressive prediction model as an example, since the operation sample data of service includes the cpu busy percentage of resource node, memory
Utilization rate, network interface card go out inbound traffics, monitor goes out inbound traffics and data Packet Forwarding Rate in it is a variety of;It will operation sample data and resource
Adjustment data are input to regressive prediction model, a function curve can be calculated, which can preferably be fitted
Above-mentioned operation sample data and resource adjust data;When receiving new operation data, can be calculated by the function curve
Obtain the corresponding resource adjustment data of the operation data.
Above-mentioned steps S302 describes the establishment process of resources model to step S306, continues with description resource
The step of method of adjustment.
Step S206 adjusts the resource node of operation service according to prediction result.
Above-mentioned steps obtain the prediction result of the current desired resource of the service by the history data of resource node, should
It may include the quantity of the current desired stock number of the service or required resource node in prediction result;If operation service
Current resource node is less than the stock number in prediction result, illustrates that the resource node for running the service needs dilatation, at this time may be used
Think that the service increases resource node, by stock number of the resource node dilatation of operation service into prediction result;If operation
The current resource node of service is greater than the stock number in prediction result, illustrates that the resource node for running the service needs capacity reducing,
Part resource node can be deleted from the resource node for currently running the service at this time, by the resource node capacity reducing of operation service
Stock number into prediction result.
In order to guarantee resource node adjustment stability and validity, can timing or sporadically monitored by staff
After prediction result adjustresources node, the operation data of resource node;Alternatively, if stock number and fortune in prediction result
The difference of the current resource node of row service exceeds given threshold, and alarm signal can be generated to prompt staff, by work
The resource node that adjustment operation service is adjusted according to prediction result is determined whether as personnel.
In addition, the forecasting accuracy in order to guarantee above-mentioned resources model, it can be according to prediction result more new model
Training sample data are input to resources model using the training sample data of update and are trained, with the money updated
Source prediction model;It specifically, can be using the corresponding history data of prediction result as the operation sample data updated, by this
Prediction result adjusts data as corresponding resource, is input to above-mentioned resources model again, is trained to model, with complete
At the renewal process of model.
A kind of resource adjusting method provided in an embodiment of the present invention, establishes resources mould by way of machine learning
The history data for servicing corresponding resource node is input in preset resources model by type, can predict to obtain
Service the prediction result of current desired resource;And then further according to the resource node of prediction result adjustment operation service.Which is logical
The mode for crossing machine learning establishes resources model, according to the money of the prediction result adjustment service of resources model output
Source while guaranteeing that system operates normally, improves cloud platform resource benefit so that the actual demand of resource and service be made to match
With rate, the use cost of platform user has been saved.
The embodiment of the invention provides another resource adjusting methods, and this method is on the basis of above-described embodiment the method
Upper realization;In the present embodiment, emphasis description adjusts the specific implementation of the resource node of operation service according to prediction result;It should
May include in prediction result run the service prediction total resources, for example, run the calculate node of the service number or
Nucleus number, the total memory capacity of memory node.During the adjustment, compare the resource of the prediction total resources and current operation service
The real resource total amount of node;According to comparison result, the resource node of current operation service is increased or decreased.
Specifically, if prediction total resources is less than the real resource total amount for currently running the resource node of the service,
The resource node of current operation service is reduced, so that running the total resources and prediction total resources one of the resource node of the service
It causes or close;If prediction total resources is more than the real resource total amount for currently running the resource node of the service, increase is worked as
The resource node of preceding operation service, so that running the resource node of the service and predicting that total resources is consistent or close.
As shown in figure 4, above-mentioned resource adjusting method is described in detail below:
Step S402 obtains in preset time period, services the history data of corresponding resource node;The history run
Data include that cpu busy percentage, memory usage, the network interface card of resource node go out inbound traffics, monitor goes out inbound traffics and data packet turns
It is a variety of in hair rate.
The history data is input in preset resources model by step S404, and output service is current desired
The prediction result of resource;It include the prediction total resources of operation service in the prediction result;The preset resources model is logical
The mode for crossing machine learning is established.
Step S406 determines the prediction section of operation service according to the unit resource amount of prediction total resources and resource node
Point quantity;
Step S408, the resource node quantity of comparison prediction number of nodes and current operation service;If predicting number of nodes
Amount is greater than resource node quantity, executes step S410;If predicting that number of nodes is less than resource node quantity, step is executed
S412;If predicting that number of nodes is equal to resource node quantity, terminate.
Step S410 increases the resource node of operation service according to prediction number of nodes;
Such as determine that prediction number of nodes is 10 according to the unit resource amount of prediction total resources and resource node, wherein transporting
Operator node 4, memory node 6, the quantity of the resource node of current operation service is 7, wherein operation node 4, storage
It node 3, is found by comparison, needs to increase by 3 memory nodes.
In actual implementation, monitoring node can notify the Resource Management node of cloud platform, more to service distribution
Resource node, so that the total resources of operation service matches with prediction total resources;Resource Management node is service distribution
After newly-increased resource node, it can be assigned information to monitoring node feeding back, newly-increased resource section is generally comprised in the information
The information such as access path, the node identification of point, so that newly-increased resource node is included in monitoring range by monitoring node.
Step S412 reduces the resource node of operation service according to prediction number of nodes.
Such as determine that prediction number of nodes is 7 according to the unit resource amount of prediction total resources and resource node, wherein transporting
Operator node 4, memory node 3, the quantity of the resource node of current operation service is 9, wherein operation node 4, storage
It node 5, is found by comparison, it is desirable to reduce 2 memory nodes.
The lower resource node of resource utilization can be selected and make according to the operating condition of each resource node by monitoring node
For resource node to be deleted;The operation procedure, data etc. of the resource node to be deleted is transferred in other resource nodes;
Later, monitoring node notice Resource Management node recycles the resource node to be deleted, after the completion of recycling, monitors node from monitoring
The resource node is deleted in range.
In above-mentioned resource adjusting method, current operation service is adjusted according to the prediction total resources of resources model output
Resource node quantity while guaranteeing that system operates normally, improve so that the actual demand of resource and service be made to match
Cloud platform resource utilization has saved the use cost of platform user.
Corresponding to above method embodiment, the resource adjusting method in the present embodiment further describes increase resource node
With the detailed process for reducing resource node;As shown in figure 5, increase resource node the step of specifically include it is as follows:
Step S500 determines resource node to be increased;
Step S502 obtains the image file of service;
The image file is that a series of specific files are fabricated to single file according to certain format, mirror image text
The operation program for running above-mentioned service is preserved in part.
The operating parameter of increased resource node is arranged in step S504;The operating parameter includes at least the number of resource node
According to transmission bandwidth;
Specifically, the specific functional modules for the service that can be executed according to the resource node, are arranged data transfer bandwidth;Example
Such as, if the resource node is mainly used for receiving transmitting file, which needs to be arranged higher upstream bandwidth;If
The resource node is mainly used for playing video file, then the resource node needs to be arranged higher downlink bandwidth.It is appreciated that also
Other operating parameters of the resource node, such as data Packet Forwarding Rate can be set.
Image file is deployed in increased resource node by step S506, and above-mentioned service is arranged in the resource section
Point in.
After operating parameter is provided with, image file can be installed into the resource node, after being installed, the resource
Node can operate normally service.
As shown in fig. 6, reduce resource node the step of specifically include it is as follows:
Step S602 determines resource node to be deleted;
As described above, the lower money of utilization rate can be selected according to the utilization rate of each resource node of operation service
Source node is as resource node to be deleted.
Step S604 is recycled in resource node to be deleted, the operation data of service;
The operation data may include operation program, the data etc. generated in operational process.
The operation data of recycling is transferred in the resource node in addition to resource node to be deleted by step S606;It will
Service in the resource node to be deleted is deleted.
By taking memory node as an example, if the memory node of current operation service shares 5, wherein determining that two are to be deleted
Resource node;At this point, recycling the operation data of the service in the two resource nodes to be deleted, and the operation that will be recovered to
Data are transferred in the resource node in addition to resource node to be deleted, that is, are transferred to remaining 3 not deleted storage sections
In point, and then delete the service in resource node to be deleted.
Step S608 deletes resource node to be deleted, after finishing the operation data transfer of recycling by not
Deleted resource node continues to run current service.
In aforesaid way, if necessary to increase resource node, then need to newly-increased resource node deployment image file simultaneously
Operating parameter is set;If necessary to reduce resource node, then need to return the operation data on resource node to be deleted
It receives and shifts;To guarantee to complete the adjustment of resource node in the case where the service of not influencing operates normally, make resource and service
Actual demand more match, improve cloud platform resource utilization, saved the use cost of platform user.
Corresponding to above method embodiment, the embodiment of the invention also provides a kind of resources to adjust device, as shown in fig. 7,
Wherein, which is applied to the monitoring node of cloud platform, which is connected with multiple resource nodes, runs on resource node
There is service;The device includes:
Data acquisition module 110, for obtaining in preset time period, the history data of the resource node;History
Operation data includes that cpu busy percentage, memory usage, the network interface card of resource node go out inbound traffics, monitor goes out inbound traffics and data
At least one of Packet Forwarding Rate;
Prediction module 111, for history data to be input in preset resources model, output service is current
The prediction result of required resource;Preset resources model is established by way of machine learning;
Module 112 is adjusted, for adjusting the resource node of operation service according to prediction result.
Specifically, above-mentioned apparatus further includes machine learning module, which is used for: obtaining number of training
According to;Operation sample data comprising at least one service in training sample data, and the corresponding resource tune of operation sample data
Entire data;Build initial model structure;Training sample data are input to initial model structure to be trained, obtain resource
Prediction model.
Specifically, above-mentioned prediction result includes the prediction total resources for running the service;Above-mentioned adjustment module 112 is used
In: the real resource total amount of comparison prediction total resources and the resource node of current operation service;According to comparison result, increase or
Reduce the resource node of current operation service.
Specifically, above-mentioned adjustment module 11 is used for: according to the unit resource amount of prediction total resources and resource node, determining
The prediction number of nodes of operation service;If predicting that number of nodes is greater than the resource node quantity of current operation service, according to pre-
Survey the resource node that number of nodes increases operation service;If predicting that number of nodes is less than the resource node number of current operation service
Amount reduces the resource node of operation service according to prediction number of nodes.
Specifically, above-mentioned adjustment module is used for: determining resource node to be increased;Obtain the image file of service;Setting
The operating parameter of increased resource node;Operating parameter includes at least the data transfer bandwidth of resource node;By image file portion
Administration will service and be arranged in resource node into increased resource node;According to operating parameter operation service.
Specifically, above-mentioned adjustment module is used for: determining resource node to be deleted;It recycles in resource node to be deleted,
The operation data of service;Operation data is transferred in the resource node in addition to resource node to be deleted;It will be to be deleted
Service in resource node is deleted.
Specifically, above-mentioned apparatus further include: data update module, for updating training sample data according to prediction result;
Training module is input to resources model for the training sample data using update and is trained, with the money updated
Source prediction model.
The embodiment of the invention provides a kind of resources to adjust device, and resources mould is established by way of machine learning
The history data for servicing corresponding resource node is input in preset resources model by type, can predict to obtain
Service the prediction result of current desired resource;And then further according to the resource node of prediction result adjustment operation service.Which is logical
The mode for crossing machine learning establishes resources model, according to the money of the prediction result adjustment service of resources model output
Source while guaranteeing that system operates normally, improves cloud platform resource benefit so that the actual demand of resource and service be made to match
With rate, the use cost of platform user has been saved.
Corresponding to foregoing invention embodiment, the embodiment of the invention also provides a kind of cloud platform, which includes monitoring
Node and resource node;Monitoring node is connected with multiple resource nodes, and operation has service on resource node;Resource node includes fortune
Operator node and/or memory node;Above-mentioned resource adjustment device is set to monitoring node.
Cloud platform provided in an embodiment of the present invention, with resource adjusting method provided by the above embodiment technology having the same
Feature reaches identical technical effect so also can solve identical technical problem.
The embodiment of the invention also provides a kind of servers, shown in Figure 8 for running above-mentioned resource adjusting method,
The Cloud Server includes memory and processor, wherein memory for store one or more computer instruction, one or more
Computer instruction is executed by processor, to realize above-mentioned resource adjusting method.
Further, Cloud Server shown in Fig. 8 further includes bus 102 and communication interface 103, processor 101, communication interface
103 and memory 100 connected by bus 102.
Wherein, memory 100 may include high-speed random access memory (RAM, Random Access Memory),
It may further include non-labile memory (non-volatile memory), for example, at least a magnetic disk storage.By extremely
A few communication interface 103 (can be wired or wireless) is realized logical between the system network element and at least one other network element
Letter connection, can be used internet, wide area network, local network, Metropolitan Area Network (MAN) etc..Bus 102 can be isa bus, pci bus or
Eisa bus etc..The bus can be divided into address bus, data/address bus, control bus etc..Only to be used in Fig. 8 convenient for indicating
One four-headed arrow indicates, it is not intended that an only bus or a type of bus.
Processor 101 may be a kind of IC chip, the processing capacity with signal.It is above-mentioned during realization
Each step of method can be completed by the integrated logic circuit of the hardware in processor 101 or the instruction of software form.On
The processor 101 stated can be general processor, including central processing unit (Central Processing Unit, abbreviation
CPU), network processing unit (Network Processor, abbreviation NP) etc.;It can also be digital signal processor (Digital
Signal Processing, abbreviation DSP), specific integrated circuit (Application Specific Integrated
Circuit, abbreviation ASIC), ready-made programmable gate array (Field-Programmable Gate Array, abbreviation FPGA) or
Person other programmable logic device, discrete gate or transistor logic, discrete hardware components.It may be implemented or execute sheet
Disclosed each method, step and logic diagram in inventive embodiments.General processor can be microprocessor or the processing
Device is also possible to any conventional processor etc..The step of method in conjunction with disclosed in the embodiment of the present invention, can be embodied directly in
Hardware decoding processor executes completion, or in decoding processor hardware and software module combination execute completion.Software mould
Block can be located at random access memory, flash memory, read-only memory, programmable read only memory or electrically erasable programmable storage
In the storage medium of this fields such as device, register maturation.The storage medium is located at memory 100, and processor 101 reads memory
Information in 100, in conjunction with its hardware complete previous embodiment method the step of.
The embodiment of the invention also provides a kind of machine readable storage medium, which is stored with machine
Executable instruction, for the machine-executable instruction when being called and being executed by processor, machine-executable instruction promotes processor real
Existing above-mentioned resource adjusting method, specific implementation can be found in embodiment of the method, and details are not described herein.
The computer program product of resource adjusting method, device provided by the embodiment of the present invention and cloud platform, including deposit
The computer readable storage medium of program code is stored up, the instruction that said program code includes can be used for executing previous methods implementation
Method described in example, specific implementation can be found in embodiment of the method, and details are not described herein.
It, can be with if the function is realized in the form of SFU software functional unit and when sold or used as an independent product
It is stored in a computer readable storage medium.Based on this understanding, technical solution of the present invention is substantially in other words
The part of the part that contributes to existing technology or the technical solution can be embodied in the form of software products, the meter
Calculation machine software product is stored in a storage medium, including some instructions are used so that a computer equipment (can be a
People's computer, server or network equipment etc.) it performs all or part of the steps of the method described in the various embodiments of the present invention.
And storage medium above-mentioned includes: that USB flash disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), arbitrary access are deposited
The various media that can store program code such as reservoir (RAM, Random Access Memory), magnetic or disk.
Finally, it should be noted that embodiment described above, only a specific embodiment of the invention, to illustrate the present invention
Technical solution, rather than its limitations, scope of protection of the present invention is not limited thereto, although with reference to the foregoing embodiments to this hair
It is bright to be described in detail, those skilled in the art should understand that: anyone skilled in the art
In the technical scope disclosed by the present invention, it can still modify to technical solution documented by previous embodiment or can be light
It is readily conceivable that variation or equivalent replacement of some of the technical features;And these modifications, variation or replacement, do not make
The essence of corresponding technical solution is detached from the spirit and scope of technical solution of the embodiment of the present invention, should all cover in protection of the invention
Within the scope of.Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (17)
1. a kind of resource adjusting method, which is characterized in that the method is applied to monitoring node, and the monitoring node is connected with more
A resource node, operation has service on the resource node, which comprises
It obtains in preset time period, the history data of the resource node;The history data includes the resource
Cpu busy percentage, memory usage, the network interface card of node go out inbound traffics, monitor goes out inbound traffics and data Packet Forwarding Rate at least
It is a kind of;
The history data is input in preset resources model, to export the current desired resource of service
Prediction result;The preset resources model is established by way of machine learning;
According to the prediction result, adjustment runs the resource node of the service.
2. the method according to claim 1, wherein the preset resources model is especially by following sides
Formula is established:
Obtain training sample data;It include the operation sample data of at least one service in the training sample data, with
And the corresponding resource of the operation sample data adjusts data;
Build initial model structure;
The training sample data are input to the initial model structure to be trained, obtain the resources model.
3. the method according to claim 1, wherein
It include the prediction total resources for running the service in the prediction result;
It is described according to the prediction result, the resource node that adjustment runs the service includes:
Compare the real resource total amount of the prediction total resources and the resource node for currently running the service;
According to comparison result, the resource node for currently running the service is increased or decreased.
4. according to the method described in claim 3, it is characterized in that, the prediction total resources and current operation institute
The real resource total amount for stating the resource node of service includes:
According to the unit resource amount of the prediction total resources and resource node, the prediction number of nodes for running the service is determined
Amount;
The resource node quantity for comparing the prediction number of nodes and currently running the service;
It is described according to comparison result, if increased or decreased, currently to run the resource node of the service include: prediction section
Point quantity is greater than the resource node quantity for currently running the service, increases according to the prediction number of nodes and runs the service
Resource node;If the prediction number of nodes is less than the resource node quantity for currently running the service, according to described pre-
It surveys number of nodes and reduces the resource node for running the service.
5. according to the method described in claim 4, it is characterized in that, described increase described in operation according to the prediction number of nodes
The resource node of service includes:
Determine resource node to be increased;
Obtain the image file of the service;
The operating parameter of resource node to be increased is set;The data that the operating parameter includes at least the resource node are transmitted
Bandwidth;
The image file is deployed in the resource node to be increased, the service is arranged in the resource node
In;
The service is run according to the operating parameter.
6. according to the method described in claim 4, it is characterized in that, described reduced described in operation according to the prediction number of nodes
The resource node of service includes:
Determine resource node to be deleted;
It recycles in the resource node to be deleted, the operation data of the service;
The operation data is transferred in the resource node in addition to the resource node to be deleted;
The service in the resource node to be deleted is deleted.
7. according to the method described in claim 2, it is characterized in that, the prediction knot of the output current desired resource of service
After the step of fruit, the method also includes:
The training sample data are updated according to the prediction result;
It is input to the resources model using the training sample data of the update to be trained, described in being updated
Resources model.
8. a kind of resource adjusts device, which is characterized in that described device is applied to monitoring node, and the monitoring node is connected with more
A resource node, operation has service on the resource node;Described device includes:
Data acquisition module, for obtaining in preset time period, the history data of the resource node;The history run
Data include that cpu busy percentage, memory usage, the network interface card of the resource node go out inbound traffics, monitor goes out inbound traffics and data
At least one of Packet Forwarding Rate;
Prediction module, for the history data to be input in preset resources model, to export the service
The prediction result of current desired resource;The preset resources model is established by way of machine learning;
Module is adjusted, for according to the prediction result, adjustment to run the resource node of the service.
9. device according to claim 8, which is characterized in that described device further includes machine learning module, the machine
Study module is used for:
Obtain training sample data;Operation sample data comprising at least one service in the training sample data, Yi Jisuo
State the corresponding resource adjustment data of operation sample data;
Build initial model structure;
The training sample data are input to the initial model structure to be trained, obtain the resources model.
10. device according to claim 8, which is characterized in that the prediction result includes running the prediction of the service
Total resources;
The adjustment module is used for: the practical money of the prediction total resources and the resource node for currently running the service
Source total amount;According to comparison result, the resource node for currently running the service is increased or decreased.
11. device according to claim 10, which is characterized in that the adjustment module is used for:
According to the unit resource amount of the prediction total resources and resource node, the prediction number of nodes for running the service is determined
Amount;
If the prediction number of nodes is greater than the resource node quantity for currently running the service, according to the prediction number of nodes
Amount increases the resource node for running the service;
If the prediction number of nodes is less than the resource node quantity for currently running the service, according to the prediction number of nodes
Amount reduces the resource node for running the service.
12. device according to claim 11, which is characterized in that the adjustment module is used for:
Determine resource node to be increased;
Obtain the image file of the service;
The operating parameter of increased resource node is set;The operating parameter includes at least the output transmission of the resource node
It is wide;
The image file is deployed in the increased resource node, the service is arranged in the resource node
In;
The service is run according to the operating parameter.
13. device according to claim 11, which is characterized in that the adjustment module is used for:
Determine resource node to be deleted;
It recycles in the resource node to be deleted, the operation data of the service;
The operation data is transferred in the resource node in addition to the resource node to be deleted;
The service in the resource node to be deleted is deleted.
14. device according to claim 9, which is characterized in that described device further include:
Data update module, for updating the training sample data according to the prediction result;
Training module is input to the resources model for the training sample data using the update and is trained, with
The resources model updated.
15. a kind of cloud platform, which is characterized in that the cloud platform includes monitoring node and resource node;The monitoring node connects
Multiple resource nodes are connected to, operation has service on the resource node;The resource node includes operation node and/or deposits
Store up node;The described in any item devices of claim 8-14 are set to the monitoring node.
16. a kind of server, which is characterized in that including processor and memory, the memory is stored with can be by the place
The machine-executable instruction that device executes is managed, the processor executes the machine-executable instruction to realize claim 1 to 7 times
Method described in one.
17. a kind of machine readable storage medium, which is characterized in that the machine readable storage medium is stored with the executable finger of machine
It enables, for the machine-executable instruction when being called and being executed by processor, machine-executable instruction promotes processor to realize that right is wanted
Seek 1 to 7 described in any item methods.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811166697.4A CN109284871A (en) | 2018-09-30 | 2018-09-30 | Resource adjusting method, device and cloud platform |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811166697.4A CN109284871A (en) | 2018-09-30 | 2018-09-30 | Resource adjusting method, device and cloud platform |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109284871A true CN109284871A (en) | 2019-01-29 |
Family
ID=65177102
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811166697.4A Pending CN109284871A (en) | 2018-09-30 | 2018-09-30 | Resource adjusting method, device and cloud platform |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109284871A (en) |
Cited By (26)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109976916A (en) * | 2019-04-04 | 2019-07-05 | 中国联合网络通信集团有限公司 | A kind of cloud resource demand determination method and system |
CN110059858A (en) * | 2019-03-15 | 2019-07-26 | 深圳壹账通智能科技有限公司 | Server resource prediction technique, device, computer equipment and storage medium |
CN110297713A (en) * | 2019-05-22 | 2019-10-01 | 菜鸟智能物流控股有限公司 | Configuration management system and method of cloud host |
CN110333991A (en) * | 2019-05-30 | 2019-10-15 | 武汉科技大学 | Cloud platform task maximum resource utilization prediction technique |
CN110365765A (en) * | 2019-07-11 | 2019-10-22 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device of cache server |
CN110673954A (en) * | 2019-09-18 | 2020-01-10 | 北京北科融智云计算科技有限公司 | Utilization rate prediction method, utilization rate prediction device, computing equipment, storage medium and program product |
CN110795334A (en) * | 2019-09-09 | 2020-02-14 | 连连银通电子支付有限公司 | Testing device and method |
CN110990138A (en) * | 2019-12-04 | 2020-04-10 | 北京三快在线科技有限公司 | Resource scheduling method, device, server and storage medium |
CN111061564A (en) * | 2019-12-11 | 2020-04-24 | 中国建设银行股份有限公司 | Server capacity adjusting method and device and electronic equipment |
CN111352712A (en) * | 2020-02-25 | 2020-06-30 | 程瑞萍 | Cloud computing task tracking processing method and device, cloud computing system and server |
CN111352733A (en) * | 2020-02-26 | 2020-06-30 | 北京奇艺世纪科技有限公司 | Capacity expansion and reduction state prediction method and device |
CN111538597A (en) * | 2020-04-27 | 2020-08-14 | 贝壳技术有限公司 | Resource allocation method and device, computer readable storage medium and electronic equipment |
CN111598390A (en) * | 2019-10-16 | 2020-08-28 | 中国南方电网有限责任公司 | Server high availability evaluation method, device, equipment and readable storage medium |
CN111858015A (en) * | 2019-04-25 | 2020-10-30 | 中国移动通信集团河北有限公司 | Method, device and gateway for configuring running resources of application program |
CN112346846A (en) * | 2019-08-06 | 2021-02-09 | 陆明 | Method and device for analyzing and arranging cloud resources and storage medium |
CN112463391A (en) * | 2020-12-08 | 2021-03-09 | Oppo广东移动通信有限公司 | Memory control method, memory control device, storage medium and electronic equipment |
CN112559147A (en) * | 2020-12-08 | 2021-03-26 | 和美(深圳)信息技术股份有限公司 | Dynamic matching algorithm, system and equipment based on GPU resource occupation characteristics |
CN112612305A (en) * | 2020-12-04 | 2021-04-06 | 格力电器(武汉)有限公司 | Temperature adjusting method, device, equipment, storage medium and air conditioning system |
CN112667405A (en) * | 2021-01-05 | 2021-04-16 | 田宇 | Information processing method, device, equipment and storage medium |
CN112860442A (en) * | 2021-03-16 | 2021-05-28 | 迅雷计算机(深圳)有限公司 | Resource quota adjusting method and device, computer equipment and storage medium |
CN113296951A (en) * | 2021-05-31 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Resource allocation scheme determination method and equipment |
CN113516270A (en) * | 2020-10-30 | 2021-10-19 | 腾讯科技(深圳)有限公司 | Service data monitoring method and device |
CN113792971A (en) * | 2021-08-11 | 2021-12-14 | 邹平市供电有限公司 | Regional power dispatching networking method and system |
US11663505B2 (en) | 2020-03-10 | 2023-05-30 | International Business Machines Corporation | Estimating performance and required resources from shift-left analysis |
CN116600015A (en) * | 2023-07-18 | 2023-08-15 | 湖南快乐阳光互动娱乐传媒有限公司 | Resource node adjustment method, system, electronic equipment and readable storage medium |
CN117729114A (en) * | 2024-01-18 | 2024-03-19 | 苏州元脑智能科技有限公司 | Network card power consumption adjustment method and device, network card, electronic equipment and storage medium |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106789424A (en) * | 2016-12-21 | 2017-05-31 | 携程旅游网络技术(上海)有限公司 | Server liveness detecting system and method |
CN107196869A (en) * | 2017-07-14 | 2017-09-22 | 北京知道创宇信息技术有限公司 | The adaptive load balancing method, apparatus and system of Intrusion Detection based on host actual loading |
CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
CN108009016A (en) * | 2016-10-31 | 2018-05-08 | 华为技术有限公司 | A kind of balancing resource load control method and colony dispatching device |
US20180144251A1 (en) * | 2016-11-23 | 2018-05-24 | Institute For Information Industry | Server and cloud computing resource optimization method thereof for cloud big data computing architecture |
-
2018
- 2018-09-30 CN CN201811166697.4A patent/CN109284871A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108009016A (en) * | 2016-10-31 | 2018-05-08 | 华为技术有限公司 | A kind of balancing resource load control method and colony dispatching device |
US20180144251A1 (en) * | 2016-11-23 | 2018-05-24 | Institute For Information Industry | Server and cloud computing resource optimization method thereof for cloud big data computing architecture |
CN106789424A (en) * | 2016-12-21 | 2017-05-31 | 携程旅游网络技术(上海)有限公司 | Server liveness detecting system and method |
CN107196869A (en) * | 2017-07-14 | 2017-09-22 | 北京知道创宇信息技术有限公司 | The adaptive load balancing method, apparatus and system of Intrusion Detection based on host actual loading |
CN107231264A (en) * | 2017-07-25 | 2017-10-03 | 北京百度网讯科技有限公司 | For the method and apparatus for the capacity for managing Cloud Server |
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN110059858A (en) * | 2019-03-15 | 2019-07-26 | 深圳壹账通智能科技有限公司 | Server resource prediction technique, device, computer equipment and storage medium |
CN109976916A (en) * | 2019-04-04 | 2019-07-05 | 中国联合网络通信集团有限公司 | A kind of cloud resource demand determination method and system |
CN111858015A (en) * | 2019-04-25 | 2020-10-30 | 中国移动通信集团河北有限公司 | Method, device and gateway for configuring running resources of application program |
CN110297713A (en) * | 2019-05-22 | 2019-10-01 | 菜鸟智能物流控股有限公司 | Configuration management system and method of cloud host |
CN110333991A (en) * | 2019-05-30 | 2019-10-15 | 武汉科技大学 | Cloud platform task maximum resource utilization prediction technique |
CN110333991B (en) * | 2019-05-30 | 2022-11-25 | 武汉科技大学 | Method for predicting maximum resource utilization rate of cloud platform tasks |
CN110365765A (en) * | 2019-07-11 | 2019-10-22 | 网宿科技股份有限公司 | A kind of bandwidth scheduling method and device of cache server |
CN112346846A (en) * | 2019-08-06 | 2021-02-09 | 陆明 | Method and device for analyzing and arranging cloud resources and storage medium |
CN110795334A (en) * | 2019-09-09 | 2020-02-14 | 连连银通电子支付有限公司 | Testing device and method |
CN110795334B (en) * | 2019-09-09 | 2023-12-29 | 连连银通电子支付有限公司 | Testing device and method |
CN110673954B (en) * | 2019-09-18 | 2022-02-15 | 北京北科融智云计算科技有限公司 | Utilization rate prediction method, utilization rate prediction device, computing equipment, storage medium and program product |
CN110673954A (en) * | 2019-09-18 | 2020-01-10 | 北京北科融智云计算科技有限公司 | Utilization rate prediction method, utilization rate prediction device, computing equipment, storage medium and program product |
CN111598390A (en) * | 2019-10-16 | 2020-08-28 | 中国南方电网有限责任公司 | Server high availability evaluation method, device, equipment and readable storage medium |
CN111598390B (en) * | 2019-10-16 | 2023-12-01 | 中国南方电网有限责任公司 | Method, device, equipment and readable storage medium for evaluating high availability of server |
CN110990138A (en) * | 2019-12-04 | 2020-04-10 | 北京三快在线科技有限公司 | Resource scheduling method, device, server and storage medium |
CN111061564A (en) * | 2019-12-11 | 2020-04-24 | 中国建设银行股份有限公司 | Server capacity adjusting method and device and electronic equipment |
CN111352712A (en) * | 2020-02-25 | 2020-06-30 | 程瑞萍 | Cloud computing task tracking processing method and device, cloud computing system and server |
CN111352733A (en) * | 2020-02-26 | 2020-06-30 | 北京奇艺世纪科技有限公司 | Capacity expansion and reduction state prediction method and device |
US11663505B2 (en) | 2020-03-10 | 2023-05-30 | International Business Machines Corporation | Estimating performance and required resources from shift-left analysis |
CN111538597B (en) * | 2020-04-27 | 2024-02-27 | 贝壳技术有限公司 | Resource allocation method, device, computer readable storage medium and electronic equipment |
CN111538597A (en) * | 2020-04-27 | 2020-08-14 | 贝壳技术有限公司 | Resource allocation method and device, computer readable storage medium and electronic equipment |
CN113516270A (en) * | 2020-10-30 | 2021-10-19 | 腾讯科技(深圳)有限公司 | Service data monitoring method and device |
CN112612305B (en) * | 2020-12-04 | 2022-04-08 | 格力电器(武汉)有限公司 | Temperature adjusting method, device, equipment, storage medium and air conditioning system |
CN112612305A (en) * | 2020-12-04 | 2021-04-06 | 格力电器(武汉)有限公司 | Temperature adjusting method, device, equipment, storage medium and air conditioning system |
CN112463391A (en) * | 2020-12-08 | 2021-03-09 | Oppo广东移动通信有限公司 | Memory control method, memory control device, storage medium and electronic equipment |
CN112559147A (en) * | 2020-12-08 | 2021-03-26 | 和美(深圳)信息技术股份有限公司 | Dynamic matching algorithm, system and equipment based on GPU resource occupation characteristics |
CN112463391B (en) * | 2020-12-08 | 2023-06-13 | Oppo广东移动通信有限公司 | Memory control method, memory control device, storage medium and electronic equipment |
CN112559147B (en) * | 2020-12-08 | 2024-04-19 | 和美(深圳)信息技术股份有限公司 | Dynamic matching method, system and equipment based on GPU (graphics processing Unit) occupied resource characteristics |
CN112667405A (en) * | 2021-01-05 | 2021-04-16 | 田宇 | Information processing method, device, equipment and storage medium |
CN112667405B (en) * | 2021-01-05 | 2021-09-24 | 田宇 | Information processing method, device, equipment and storage medium |
CN112860442A (en) * | 2021-03-16 | 2021-05-28 | 迅雷计算机(深圳)有限公司 | Resource quota adjusting method and device, computer equipment and storage medium |
CN113296951A (en) * | 2021-05-31 | 2021-08-24 | 阿里巴巴新加坡控股有限公司 | Resource allocation scheme determination method and equipment |
CN113792971A (en) * | 2021-08-11 | 2021-12-14 | 邹平市供电有限公司 | Regional power dispatching networking method and system |
CN113792971B (en) * | 2021-08-11 | 2023-12-29 | 邹平市供电有限公司 | Regional power dispatching networking method and system |
CN116600015A (en) * | 2023-07-18 | 2023-08-15 | 湖南快乐阳光互动娱乐传媒有限公司 | Resource node adjustment method, system, electronic equipment and readable storage medium |
CN116600015B (en) * | 2023-07-18 | 2023-10-10 | 湖南快乐阳光互动娱乐传媒有限公司 | Resource node adjustment method, system, electronic equipment and readable storage medium |
CN117729114A (en) * | 2024-01-18 | 2024-03-19 | 苏州元脑智能科技有限公司 | Network card power consumption adjustment method and device, network card, electronic equipment and storage medium |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109284871A (en) | Resource adjusting method, device and cloud platform | |
CN111158613B (en) | Data block storage method and device based on access heat and storage equipment | |
CN107333292B (en) | A kind of SIM card state judging method and device | |
CN105471759A (en) | Network traffic scheduling method and apparatus for data centers | |
CN104901989B (en) | A kind of Site Service offer system and method | |
EP3136650B1 (en) | Method and system for optimizing network parameters to improve customer satisfaction of network content | |
CN108089921A (en) | Server for cloud big data operation architecture and operation resource optimization method thereof | |
CN107690822A (en) | Network management | |
CN111126621B (en) | Online model training method and device | |
CN103701934A (en) | Resource optimal scheduling method and virtual machine host machine optimal selection method | |
CN111143039B (en) | Scheduling method and device of virtual machine and computer storage medium | |
Alasmari et al. | Mobile edge offloading using markov decision processes | |
CN106020976A (en) | Method and apparatus for offloading out of memory processing process to user space | |
CN110533489A (en) | Sample acquiring method and device, equipment, storage medium applied to model training | |
CN109471783A (en) | The method and apparatus for predicting task run parameter | |
CN106797399A (en) | Determine collocation method, equipment, system and the computer-readable medium of the new configuration of computing resource | |
CN106775885A (en) | A kind of daily record output control method and system and bank management system | |
CN106453143A (en) | Bandwidth setting method, device and system | |
GB2599196A (en) | Continuous network slicing in a 5G cellular communications network via a delayed deep deterministic policy gradient | |
CN110019261A (en) | Data query method and apparatus | |
CN104866375B (en) | A kind of method and device for migrating virtual machine | |
CN115774602A (en) | Container resource allocation method, device, equipment and storage medium | |
CN114978913B (en) | Cross-domain deployment method and system for service function chains based on cut chains | |
CN109978172B (en) | Resource pool utilization rate prediction method and device based on extreme learning machine | |
WO2017213065A1 (en) | Service management system, service management method, and recording medium |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190129 |